## Background Signature V2 capability: decide whether memory is trustworthy enough for an agent action. ## Problem Statement Retrieval returns memory without ACT/VERIFY/ASK/ESCALATE/BLOCK policy. One confidence score is overloaded for action risk. ## Proposed Solution - Package `reliability/` (gate, risk, policies, reason_codes, confidence) - Action risk enum: READ_ONLY … PRIVILEGED - Separate memory_confidence vs action_confidence (risk-dependent thresholds) - Typed decisions: ACT | VERIFY | ASK | ESCALATE | BLOCK - `POST /reliability/evaluate` + MCP `cortex_evaluate` - Authorization outside the LLM; no ACT without permission ## Acceptance Criteria - [ ] Same memory → different decisions by action risk - [ ] High memory confidence ≠ automatic high action confidence - [ ] Unauthorized caller cannot get ACT for restricted actions - [ ] Auditable reason_codes - [ ] Signature scenario: restart payments → BLOCK with evidence ## Depends on Evidence Graph + Temporal Truth (gate inputs) ## Plan ref todo `reliability-gate` — V2 Enhancement 1
Activity
V2 P0: Memory Reliability Gate API and MCP cortex_evaluate (#71).
Merge pull request #85 from askmy-stack/cursor/v2-reliability-gate-b994